© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 153997
    Prev
    Next
    INDEX
    Explanations

    Arabic script

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beispiel
    0.58
     misschien
    0.56
     لكن
    0.56
     vielleicht
    0.54
    的一個
    0.54
     Deshalb
    0.53
    沒
    0.52
     但是
    0.51
     Leute
    0.50
     exempel
    0.50
    POSITIVE LOGITS
    َی
    0.80
    انی
    0.76
    ِی
    0.76
     فی
    0.74
     ی
    0.69
    ین
    0.68
     کل
    0.68
    ką
    0.68
    وی
    0.66
    بی
    0.66
    Activations Density 0.000%

    No Known Activations